Skip to content

Ensuring the cropping transform is invertible #1262

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 25, 2023
Merged

Ensuring the cropping transform is invertible #1262

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d06f004
ensure invertible
myron Mar 22, 2023
a1fcf5b
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Mar 22, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions auto3dseg/tasks/hecktor22/hecktor_crop_neck_region.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,9 @@ def __call__(self, data):

box_start, box_end = self.extract_roi(im_pet=im_pet, box_size=box_size)

if "label" in d and "label" in self.keys:
use_label = "label" in d and "label" in self.keys and (d["image"].shape[1:] == d["label"].shape[1:])

if use_label:
# if label mask is available, let's check if the cropped region includes all foreground
before_sum = d["label"].sum().item()
after_sum = (
Expand Down Expand Up @@ -83,7 +85,8 @@ def __call__(self, data):
d[self.end_coord_key] = box_end

for key, m in self.key_iterator(d, self.mode):
self.push_transform(d, key, extra_info={"box_start": box_start, "box_end": box_end})
if key == "label" and not use_label:
continue
d[key] = self.cropper.crop_pad(img=d[key], box_start=box_start, box_end=box_end, mode=m)

return d
Expand Down